Synonym Expansion for Large Shopping Taxonomies

We present an approach for expanding taxonomies with synonyms, or aliases. We target large shopping taxonomies, with thousands of nodes. A comprehensive set of entity aliases is an important component of identifying entities in unstructured text such as product reviews or search queries. Our method consists of two stages: we generate synonym candidates from WordNet and shopping search queries, then use a binary classii¬er to i¬lter candidates. We process taxonomies with thousands of synonyms in order to generate over 90,000 synonyms. We show that using the taxonomy to derive contextual features improves classii¬cation performance over using features from the target node alone.We show that our approach has potential for transfer learning between dii¬€erent taxonomy domains, which reduces the need to collect training data for new taxonomies.